We are excited to share our latest work: CoV: Chain-of-View Prompting for Spatial Reasoning.
CoV is a multi-step reasoning Embodied QA agent framework that enables VLMs to actively acquire more question-relevant viewpoints.
Project on ziplab.co/CoV/
ziplab.co
CoV - A multi-step EQA Agent Framework
CoV is a multi-step reasoning Embodied QA agent framework that enables VLMs to actively acquire more question-relevant viewpoints.